基于相似日选取样本的短期风电功率混沌预测

Short-Term Wind Power Forecasting Based on Trend-Similar Days and Chaotic Time Series

为减小构成初始条件的样本数据所导致的预测误差,本文借鉴负荷预测中基于相似日选取样本的思想,采用趋势相似度的概念选择相似日作为模型输入量,对短期风电功率进行混沌预测。选择我国某区域风电功率数据作为研究对象,考虑不同预测步长和季节差异,进行了大量的算例仿真,结果验证了该方法提高混沌预测精度的有效性和适用性。

In order to reduce the error brought by the input data, this paper draws the idea of selecting samples based on similar days from the load forecasting, and uses trend similarity to select similar days as the input of the forecasting model. Illustrations are made considering different forecast horizons and wind power seasonal variance. The results show that the proposed method helps to improve the accuracy effectively.